Pith. sign in

REVIEW 19 cited by

mPLUG-DocOwl 1.5: Unified Structure Learning for OCR-free Document Understanding

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2403.12895 v1 pith:25VVJVO7 submitted 2024-03-19 cs.CV

mPLUG-DocOwl 1.5: Unified Structure Learning for OCR-free Document Understanding

classification cs.CV
keywords structuredocumentunderstandingimagesinformationlearningvisualmllms
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Structure information is critical for understanding the semantics of text-rich images, such as documents, tables, and charts. Existing Multimodal Large Language Models (MLLMs) for Visual Document Understanding are equipped with text recognition ability but lack general structure understanding abilities for text-rich document images. In this work, we emphasize the importance of structure information in Visual Document Understanding and propose the Unified Structure Learning to boost the performance of MLLMs. Our Unified Structure Learning comprises structure-aware parsing tasks and multi-grained text localization tasks across 5 domains: document, webpage, table, chart, and natural image. To better encode structure information, we design a simple and effective vision-to-text module H-Reducer, which can not only maintain the layout information but also reduce the length of visual features by merging horizontal adjacent patches through convolution, enabling the LLM to understand high-resolution images more efficiently. Furthermore, by constructing structure-aware text sequences and multi-grained pairs of texts and bounding boxes for publicly available text-rich images, we build a comprehensive training set DocStruct4M to support structure learning. Finally, we construct a small but high-quality reasoning tuning dataset DocReason25K to trigger the detailed explanation ability in the document domain. Our model DocOwl 1.5 achieves state-of-the-art performance on 10 visual document understanding benchmarks, improving the SOTA performance of MLLMs with a 7B LLM by more than 10 points in 5/10 benchmarks. Our codes, models, and datasets are publicly available at https://github.com/X-PLUG/mPLUG-DocOwl/tree/main/DocOwl1.5.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 19 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence

    cs.CL 2026-05 accept novelty 8.0

    CiteVQA requires models to cite specific document regions with bounding boxes alongside answers and finds that even the strongest MLLMs frequently cite the wrong region, with top SAA scores of only 76.0 for closed mod...

  2. A document is worth a structured record: Principled inductive bias design for document recognition

    cs.CV 2025-07 unverdicted novelty 8.0

    Introduces a method to design structure-specific relational inductive biases for a base transformer architecture, enabling end-to-end transcription of documents with intrinsic structures, demonstrated on sheet music, ...

  3. MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?

    cs.CV 2024-08 conditional novelty 8.0

    MME-RealWorld is the largest manually annotated high-resolution benchmark for MLLMs, where even the best models achieve less than 60% accuracy on challenging real-world tasks.

  4. Q-Mask: Query-driven Causal Masks for Text Anchoring in OCR-Oriented Vision-Language Models

    cs.CV 2026-03 unverdicted novelty 7.0

    Q-Mask uses query-conditioned causal masks to separate text location from recognition in OCR VLMs, backed by a new benchmark and 26M-pair training dataset.

  5. CodeOCR: On the Effectiveness of Vision Language Models in Code Understanding

    cs.CL 2026-02 unverdicted novelty 7.0

    Multimodal LLMs process code as images to achieve up to 8x token compression, with visual cues like syntax highlighting aiding tasks and clone detection remaining resilient or even improving under compression.

  6. OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoning

    cs.CV 2024-12 accept novelty 7.0

    OCRBench v2 is a new benchmark with four times more tasks than prior versions that reveals most large multimodal models score below 50 out of 100 on visual text tasks and share five specific weaknesses.

  7. PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction

    cs.CV 2024-10 accept novelty 7.0

    PyramidDrop accelerates LVLMs by staged, similarity-based dropping of visual tokens that become redundant in deeper layers, delivering 40% faster training and 55% lower inference cost with comparable accuracy.

  8. Infinity-Parser2 Technical Report

    cs.AI 2026-07 conditional novelty 6.0

    An end-to-end document parser trained on 5M synthetic and mined pages with multi-task RL reaches 87.6% on olmOCR-Bench and 74.3% on ParseBench.

  9. Infinity-Parser2 Technical Report

    cs.AI 2026-07 accept novelty 6.0

    A controllable DOM synthesis flywheel plus verifiable multi-task RL yields Infinity-Parser2, with Pro at 87.6% olmOCR-Bench and 74.3% ParseBench and Flash at 3.68× prior throughput.

  10. SinkRouter: Sink-Aware Routing for Efficient Long-Context Decoding in Large Language and Multimodal Models

    cs.LG 2026-04 unverdicted novelty 6.0

    SinkRouter identifies attention sinks as training-derived fixed points and routes around them to skip redundant KV-cache loads, delivering up to 2.03x decoding speedup on long-context benchmarks.

  11. HART: High-Resolution Annotation-Free Reasoning Technique through a Closed-loop Framework

    cs.CV 2026-02 conditional novelty 6.0

    HART uses a closed-loop 'crop-and-answer' training scheme plus a dynamic-weight GRPO variant to improve LMM grounding and high-resolution reasoning without bounding-box annotations.

  12. Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling

    cs.CV 2024-12 unverdicted novelty 6.0

    InternVL 2.5 is the first open-source MLLM to surpass 70% on the MMMU benchmark via model, data, and test-time scaling, with a 3.7-point gain from chain-of-thought reasoning.

  13. Infinity-Parser2 Technical Report

    cs.AI 2026-07 unverdicted novelty 5.0

    Infinity-Parser2 pairs a 5M synthetic bilingual document corpus with multi-task RL to claim SOTA document parsing on olmOCR-Bench and ParseBench.

  14. General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model

    cs.CV 2024-09 unverdicted novelty 5.0

    GOT is a unified end-to-end model that treats all man-made optical signals as characters and handles multiple OCR tasks including formatted output and interactive region recognition via prompts.

  15. InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output

    cs.CV 2024-07 conditional novelty 5.0

    InternLM-XComposer-2.5 is a 7B vision-language model supporting up to 96K context that reaches GPT-4V-level performance on image, video, and multi-turn tasks and adds LoRA-driven text-image composition capabilities.

  16. MinerU: An Open-Source Solution for Precise Document Content Extraction

    cs.CV 2024-09 conditional novelty 4.0

    MinerU delivers an open-source pipeline for high-precision document content extraction by integrating specialized models with tuned preprocessing and postprocessing rules.

  17. How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites

    cs.CV 2024-04 unverdicted novelty 4.0

    InternVL 1.5 narrows the performance gap to proprietary multimodal models via a stronger transferable vision encoder, dynamic high-resolution tiling, and curated English-Chinese training data.

  18. Document Parsing Unveiled: Techniques, Challenges, and Prospects for Structured Information Extraction

    cs.MM 2024-10 unverdicted novelty 3.0

    Survey proposing a taxonomy for document parsing into pipeline-based systems and VLM-driven unified models, reviewing components, metrics, benchmarks, and challenges.

  19. A Survey on Multimodal Large Language Models

    cs.CV 2023-06 accept novelty 3.0

    This survey organizes the architectures, training strategies, data, evaluation methods, extensions, and challenges of Multimodal Large Language Models.